© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 235726
    Prev
    Next
    INDEX
    Explanations

    calculate relevant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Annex
    0.45
     Catalogue
    0.45
    bonded
    0.43
     못
    0.41
     WARRANTIES
    0.41
    butterfly
    0.41
     ستر
    0.40
     بُ
    0.40
     YoY
    0.40
    bevel
    0.40
    POSITIVE LOGITS
    üml
    0.57
    uyện
    0.52
     humains
    0.52
    ቛ
    0.52
    ,_-
    0.50
    ین
    0.50
    ellidos
    0.50
    人數
    0.50
    ન
    0.49
    ब्रिट
    0.49
    Activations Density 0.001%

    No Known Activations